Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numerical values and proportions in context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ant
    -0.45
     hår
    -0.44
    thong
    -0.39
     jura
    -0.38
    deltaTime
    -0.38
     
    -0.37
    uno
    -0.37
    OGEN
    -0.37
    ell
    -0.36
    est
    -0.36
    POSITIVE LOGITS
    SharedCtor
    1.12
     Roskov
    1.12
    featureID
    1.08
    RenderAtEndOf
    1.07
     resourceCulture
    1.03
    Geplaatst
    1.02
    1.00
     '\\;'
    0.99
     ModelExpression
    0.98
     Италијани
    0.96
    Act Density 0.080%

    No Known Activations